Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.4482. Min Act: -0.1700
Data Index: 5660368 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.2607. Min Act: -0.1700
Data Index: 20099 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.2607. Min Act: -0.1700
Data Index: 6291002 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.2607. Min Act: -0.1700
Data Index: 3016204 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.1357. Min Act: -0.1700
Data Index: 8164234 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.1982. Min Act: -0.1700
Data Index: 954987 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.1357. Min Act: -0.1700
Data Index: 2972589 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.1982. Min Act: -0.1700
Data Index: 5976572 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.0732. Min Act: -0.1700
Data Index: 3745750 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.0107. Min Act: -0.1700
Data Index: 4435824 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.0107. Min Act: -0.1700
Data Index: 4797639 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.0107. Min Act: -0.1700
Data Index: 1112058 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.0107. Min Act: -0.1700
Data Index: 7350666 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.0107. Min Act: -0.1700
Data Index: 397204 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4482. Min Range: -12.4482
Max Act: 11.9482. Min Act: -0.1700
Data Index: 833118 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4482. Min Range: -12.4482
Max Act: 11.9482. Min Act: -0.1700
Data Index: 7995693 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4482. Min Range: -12.4482
Max Act: 11.9482. Min Act: -0.1700
Data Index: 3285966 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4482. Min Range: -12.4482
Max Act: 11.9482. Min Act: -0.1700
Data Index: 4896112 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4482. Min Range: -12.4482
Max Act: 12.0107. Min Act: -0.1700
Data Index: 2278537 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4482. Min Range: -12.4482
Max Act: 11.9482. Min Act: -0.1700
Data Index: 5014752 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19